anaxqx

PPS-Ctrl: Colonoscopy Translation with Stable Diffusion and ControlNet

PPS-Ctrl explores sim-to-real image translation for colonoscopy depth estimation, built on Stable Diffusion and ControlNet with per-pixel shading maps as structural guidance. The repository currently provides partial pseudocode rather than a complete training and inference implementation.

View on GitHub Compare
Stars
9
Forks
1
Stars, last 30 days
+0
Last commit
5 months ago
Contributors
1

Our take

Quietno commits in the last 90 days and no release in a year

Health score

16/100

How it is scored
Activity
19
Community
4
Issues
21
Pull requests
20

+0 stars in the last 30 days

  • Fewer contributors than 91% of the projects we track

PPS-Ctrl is a promising research concept, but its current pseudocode-only state and quiet, single-contributor development make it unsuitable as a ready-to-run dependency.

Good fit if

  • You are researching colonoscopy depth estimation or sim-to-real translation and can implement from partial pseudocode.
  • Your experiments can use Stable Diffusion, ControlNet, and the Python/PyTorch/Diffusers stack.
  • You want to investigate per-pixel shading maps as a structural condition.

Look elsewhere if

  • You need complete training code, checkpoints, or a production-ready translation pipeline now.
  • Your team needs an actively maintained project with recent releases or broader contributor support.
  • You require a clearly stated license before using or adapting the code.
All health signals
Last commit2026-05-18 (5 months ago)
Commits, last 90 days0
Releases, last 12 months0
Contributors1
Issues closed, last 90 days0
Pull requests merged, last 90 days0
Project age19 months

Checked on 2026-10-16 with the GitHub API.

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

9

Forks

1

Change since Nov 17, 2026: 0 stars·0 forks

Overview

PPS-Ctrl is a research framework for translating simulated colonoscopy images toward real-image appearance to support depth estimation. It builds on Stable Diffusion and ControlNet, using per-pixel shading (PPS) maps as a physics-informed structural guide instead of relying on depth maps alone.

The intended audience is researchers working on endoscopic vision and sim-to-real transfer. The repository describes the approach and data preparation, but currently provides partial pseudocode, not a complete usable training pipeline.

Key Features

  • Uses Stable Diffusion and ControlNet for image translation.
  • Conditions translation on per-pixel shading maps that represent surface-light interactions.
  • Targets sim-to-real translation for colonoscopy depth-estimation research.
  • Describes preprocessing PPS maps from depth data with a provided command.
  • Identifies SimCol3D, C3VD, and Colon10K as relevant datasets.
  • Cites PPSNet, along with Stable Diffusion, ControlNet, and Hugging Face Diffusers, as related foundations.

Use Cases

  • Endoscopy researchers exploring structural conditioning for simulated-to-real image translation.
  • Teams studying whether shading cues can preserve geometry while adding realistic colonoscopy textures.
  • Researchers preparing depth-derived PPS maps for experiments using the named colonoscopy datasets.
  • Depth-estimation practitioners assessing a research direction before implementing or adapting a full pipeline.

What you need

Detected in the repository

  • Python (main language on GitHub)

Getting Started

The README recommends Python 3.9, PyTorch 2.0 or newer, and Hugging Face Diffusers:

conda create -n ppsctrl python=3.9
conda activate ppsctrl
pip install -r requirements.txt

See the repository README for dataset links and the PPS preprocessing command. The code is incomplete, so these steps should not be treated as a complete training setup.

License in Plain Words

No standard license was detected. Without a license, the default copyright rules apply: you may read the code, but not reuse it. Check the repository or ask the authors.

Considerations

  • The README says the repository is under construction and contains partial pseudocode; complete code and checkpoints are deferred until paper acceptance.
  • The project has had no commits in the last 90 days and no release in over a year. Its code contributions are concentrated in one person, and no issues were closed recently.
  • The README recommends Python 3.9, PyTorch 2.0 or newer, and Diffusers, but does not state hardware requirements.
  • No license is listed in the supplied repository metadata, so permissions for reuse and redistribution are unclear.

Found this useful?

Share it with someone who would like PPS-Ctrl.